AivaStack
Vouch — independently measured reliability scores for MCP tools, not self-reported claims.
AI & ModelsRemote
Loading MCP servers…
Showing 2,017–2,064 of 2,642
Vouch — independently measured reliability scores for MCP tools, not self-reported claims.
Showing 2,017–2,064 of 2,642
ClawHub.ai skill catalog: search, browse, inspect, and download skills (token unlocks publish).
Free AI test helpers: injection inputs, OWASP mapping, release plans, response and tool-call packs.
Persistent memory, task coordination, and HITL queue for AI coding sessions.
Resolve real-world capability gaps: validate native MCPs, search the web, and record unmet demand.
Search, browse, and install MCP servers, agents, skills, and plugins from conduitAI.
63 tools an LLM can't do alone, in focused subsets: file edits, live data, real checksums.
Snap decisions for coding agents: local or hosted classify/check/score/rank via MCP.
MCP Server with AI-powered tools including ElevenLabs text-to-speech for realistic voice synthesis.
Persistent memory for AI agents. Store, recall, and share knowledge across sessions.
Knowledge exchange on the future of AI for agents: sign up in one call, join sourced rounds.
Adaptive sliding window query debouncing and micro-batch coalescing engine optimizing LLM throughput
Full jitter exponential backoff retry scheduling and half-open circuit breaker for LLM APIs
Agent conversation state snapshotting and time-travel rollback engine pruning divergent hallucinatio
In-memory concurrency leaky-bucket and fair semaphore guard protecting downstream LLM APIs from rate
Consistent hashing ring with virtual nodes for distributed LLM cache routing and agent partitioning
Priority-weighted context window token pruner and FIFO eviction engine protecting LLM prompt boundar
In-memory distributed lease lock with monotonically increasing fencing tokens preventing multi-agent
Token entropy and n-gram perplexity analyzer auditing LLM outputs for degenerate repetition loops an
Maximal Marginal Relevance (MMR) exemplar selector optimizing semantic relevance and diversity for L
Tarjan strongly connected components cycle and deadlock detector for multi-agent DAG workflows
Safe zero-dependency Jinja-like prompt template parser and renderer supporting for-loops, if-conditi
Zero-dependency JSON schema subset validator ensuring LLM structured outputs strictly conform to con
Fast Levenshtein distance and fuzzy similarity matcher autocorrecting hallucinated LLM tool calls
Adaptive multi-tier TPM/RPM rate limiter with smooth leaky bucket queuing and burst wait estimation
Multi-model LLM token cost budget ledger and burn rate forecaster enforcing spending limits and earl
Positional Borda Count voting and weighted multi-agent consensus engine resolving conflicting model
Min-heap priority event scheduler and delayed task dispatcher for asynchronous multi-agent coordinat
Prompt template drift and structural fingerprint sentinel detecting unauthorized prompt mutations an
HMAC-signed zero-width invisible canary token generator and output response leak auditor
Semantic boundary preserving text chunker maintaining markdown headers, code fences, and paragraphs
Voice pipeline timestamp telemetry profiler and percentile latency calculator
Bidirectional in-memory sensitive vault and surrogate token masker protecting credentials in LLM pro
O(k) space unbiased stream reservoir sampling and quantile estimation engine for LLM telemetry and h
Token bucket traffic shaper with smooth replenishment and burst capacity for LLM tool call throttlin
Tri-state circuit breaker router managing LLM provider failure cascades, sliding error windows, and
High-performance in-memory Trie and multi-keyword search engine for prompt routing and entity extrac
Distributed Two-Phase Commit (2PC) transaction coordinator for atomic multi-agent state mutations wi
High-dimensional vector embedding semantic SimHash deduplication sentinel with LRU cache simulation
VAD energy and transcript heuristics for voice turn endpoint detection
Nginx-style smooth weighted round-robin load balancer with dynamic weight adjustment for multi-LLM r
Persistent long-term memory for Claude Desktop / Claude Code, backed by EvolutionDB.
Knowledge graph for AI agents. Query concepts, walk edges, get advisories.
Biological memory for AI agents. Pattern learning, decay, clustering, 8-drive behavior.
A neutral memory quality-gate MCP server: save_memory, recall_memory, forget_memory over stdio.
Cross-device AI memory with encrypted activity capture and context handoff between AI tools
LLM pricing where every rate carries its source and the date it was last confirmed.
One MCP endpoint for Claude, GPT & Gemini: 100+ tools + no-code connectors + agent workers.
